arXiv subjects

Tomaso Poggio

Publications and source records attributed to Tomaso Poggio.

At least 37 records · Page 2Linked to original sources

arXiv2026

A universal compression theory for lottery ticket hypothesis and neural scaling laws

When training large-scale models, the performance typically scales with the number of parameters and the dataset size according to a slow power law. A fundamental theoretical and practical question is whether comparable performance can be achieved with significantly smaller models and substantially less data. In this work, we provide a positive and constructive answer. We prove that a generic permutation-invariant function of $d$ objects can be asymptotically compressed into a function of $\operatorname{polylog} d$ objects with vanishing error, which is proved to be the optimal compression rate. This theorem yields two key implications: (Ia) a large neural network can be compressed to polylogarithmic width while preserving its learning dynamics; (Ib) a large dataset can be compressed to polylogarithmic size while leaving the loss landscape of the corresponding model unchanged. Implication (Ia) directly establishes a proof of the dynamical lottery ticket hypothesis, which states that any ordinary network can be strongly compressed such that the learning dynamics and result remain unchanged. (Ib) shows that a neural scaling law of the form $L\sim d^{-α}$ can be boosted to an arbitrarily fast power law decay, and ultimately to $\exp(-α' \sqrt[m]{d})$.

stat.ML↗

arXiv2026

Does Feedback Alignment Work at Biological Timescales?

Feedback alignment and related weight-transport-free algorithms are often proposed as biologically plausible alternatives to backpropagation, yet they are typically formulated in discrete phases with implicitly synchronized forward and error signals. We develop a continuous-time model of feedback-alignment-type learning in which neural activities and synaptic weights evolve together under coupled first-order dynamics with distinct propagation, plasticity, and decay time constants. We show that learning is governed by the temporal overlap between presynaptic drive and a locally projected error signal, providing an analytic explanation for robustness to moderate timing mismatch and for failure when mismatch eliminates overlap. Our results show that in order for feedback-alignment-type algorithms to work at biological timescales, they must obey the same temporal overlap principle that applies to other biological processes like eligibility traces.

cs.LG↗

arXiv2026

Probing Neural Topology of Large Language Models

Probing large language models (LLMs) has yielded valuable insights into their internal mechanisms by linking neural activations to interpretable semantics. However, the complex mechanisms that link neuron's functional co-activation with the emergent model capabilities remains largely unknown, hindering a deeper understanding and safer development of LLMs. In this work, we introduce graph probing, a method for uncovering the functional connectivity of LLM neurons and relating it to language generation performance. By probing models across diverse LLM families and scales, we discover a universal predictability of language generation and understanding performance using only neural topology, which persists even when retaining just 1% of neuron connections. Strikingly, probing on topology outperforms probing on activation by up to 130.4% and 67.7% on perplexity and space/time semantic regression respectively, suggesting that neural topology contains orders of richer information of LLM performance than neural activation, which can be easily extracted with simple linear or MLP probes. To explain the dependence between neural topology and language performance, we identify default networks and hub neurons in LLMs and provide causal evidence by interventional experiments on multiple benchmarks, showing that LLMs actually exploit these topological information. Further analyses suggest that graph probing can be effectively leveraged to improve the efficiency and reliability of LLMs through proof-of-concept applications in model pruning and hallucination detection. Codes and data for the graph probing toolbox are available at https://github.com/DavyMorgan/llm-graph-probing.

cs.CL↗

arXiv2025

Training the Untrainable: Introducing Inductive Bias via Representational Alignment

We demonstrate that architectures which traditionally are considered to be ill-suited for a task can be trained using inductive biases from another architecture. We call a network untrainable when it overfits, underfits, or converges to poor results even when tuning their hyperparameters. For example, fully connected networks overfit on object recognition while deep convolutional networks without residual connections underfit. The traditional answer is to change the architecture to impose some inductive bias, although the nature of that bias is unknown. We introduce guidance, where a guide network steers a target network using a neural distance function. The target minimizes its task loss plus a layerwise representational similarity against the frozen guide. If the guide is trained, this transfers over the architectural prior and knowledge of the guide to the target. If the guide is untrained, this transfers over only part of the architectural prior of the guide. We show that guidance prevents FCN overfitting on ImageNet, narrows the vanilla RNN-Transformer gap, boosts plain CNNs toward ResNet accuracy, and aids Transformers on RNN-favored tasks. We further identify that guidance-driven initialization alone can mitigate FCN overfitting. Our method provides a mathematical tool to investigate priors and architectures, and in the long term, could automate architecture design.

cs.LG↗

arXiv2025

On efficiently computable functions, deep networks and sparse compositionality

We show that \emph{efficient Turing computability} at any fixed input/output precision implies the existence of \emph{compositionally sparse} (bounded-fan-in, polynomial-size) DAG representations and of corresponding neural approximants achieving the target precision. Concretely: if $f:[0,1]^d\to\R^m$ is computable in time polynomial in the bit-depths, then for every pair of precisions $(n,m_{\mathrm{out}})$ there exists a bounded-fan-in Boolean circuit of size and depth $\poly(n+m_{\mathrm{out}})$ computing the discretized map; replacing each gate by a constant-size neural emulator yields a deep network of size/depth $\poly(n+m_{\mathrm{out}})$ that achieves accuracy $\varepsilon=2^{-m_{\mathrm{out}}}$. We also relate these constructions to compositional approximation rates \cite{MhaskarPoggio2016b,poggio_deep_shallow_2017,Poggio2017,Poggio2023HowDS} and to optimization viewed as hierarchical search over sparse structures.

cs.LG↗

arXiv2025

Hierarchical Reasoning Models: Perspectives and Misconceptions

Transformers have demonstrated remarkable performance in natural language processing and related domains, as they largely focus on sequential, autoregressive next-token prediction tasks. Yet, they struggle in logical reasoning, not necessarily because of a fundamental limitation of these models, but possibly due to the lack of exploration of more creative uses, such as latent space and recurrent reasoning. An emerging exploration in this direction is the Hierarchical Reasoning Model (Wang et. al., 2025), which introduces a novel type of recurrent reasoning in the latent space of transformers, achieving remarkable performance on a wide range of 2D reasoning tasks. Despite the promising results, this line of models is still at an early stage and calls for in-depth investigation. In this work, we review this class of models, examine key design choices, test alternative variants and clarify common misconceptions.

cs.AI↗

arXiv2025

Topological Invariance and Breakdown in Learning

We prove that for a broad class of permutation-equivariant learning rules (including SGD, Adam, and others), the training process induces a bi-Lipschitz mapping between neurons and strongly constrains the topology of the neuron distribution during training. This result reveals a qualitative difference between small and large learning rates $η$. With a learning rate below a topological critical point $η^*$, the training is constrained to preserve all topological structure of the neurons. In contrast, above $η^*$, the learning process allows for topological simplification, making the neuron manifold progressively coarser and thereby reducing the model's expressivity. Viewed in combination with the recent discovery of the edge of stability phenomenon, the learning dynamics of neuron networks under gradient descent can be divided into two phases: first they undergo smooth optimization under topological constraints, and then enter a second phase where they learn through drastic topological simplifications. A key feature of our theory is that it is independent of specific architectures or loss functions, enabling the universal application of topological methods to the study of deep learning.

cs.LG↗

arXiv2025

Position: A Theory of Deep Learning Must Include Compositional Sparsity

Overparametrized Deep Neural Networks (DNNs) have demonstrated remarkable success in a wide variety of domains too high-dimensional for classical shallow networks subject to the curse of dimensionality. However, open questions about fundamental principles, that govern the learning dynamics of DNNs, remain. In this position paper we argue that it is the ability of DNNs to exploit the compositionally sparse structure of the target function driving their success. As such, DNNs can leverage the property that most practically relevant functions can be composed from a small set of constituent functions, each of which relies only on a low-dimensional subset of all inputs. We show that this property is shared by all efficiently Turing-computable functions and is therefore highly likely present in all current learning problems. While some promising theoretical insights on questions concerned with approximation and generalization exist in the setting of compositionally sparse functions, several important questions on the learnability and optimization of DNNs remain. Completing the picture of the role of compositional sparsity in deep learning is essential to a comprehensive theory of artificial, and even general, intelligence.

cs.LG↗

arXiv2025

Parameter Symmetry Potentially Unifies Deep Learning Theory

The dynamics of learning in modern large AI systems is hierarchical, often characterized by abrupt, qualitative shifts akin to phase transitions observed in physical systems. While these phenomena hold promise for uncovering the mechanisms behind neural networks and language models, existing theories remain fragmented, addressing specific cases. In this position paper, we advocate for the crucial role of the research direction of parameter symmetries in unifying these fragmented theories. This position is founded on a centralizing hypothesis for this direction: parameter symmetry breaking and restoration are the unifying mechanisms underlying the hierarchical learning behavior of AI models. We synthesize prior observations and theories to argue that this direction of research could lead to a unified understanding of three distinct hierarchies in neural networks: learning dynamics, model complexity, and representation formation. By connecting these hierarchies, our position paper elevates symmetry -- a cornerstone of theoretical physics -- to become a potential fundamental principle in modern AI.

cs.LG↗

arXiv2025

Heterosynaptic Circuits Are Universal Gradient Machines

We propose a design principle for the learning circuits of the biological brain. The principle states that almost any dendritic weights updated via heterosynaptic plasticity can implement a generalized and efficient class of gradient-based meta-learning. The theory suggests that a broad class of biologically plausible learning algorithms, together with the standard machine learning optimizers, can be grounded in heterosynaptic circuit motifs. This principle suggests that the phenomenology of (anti-) Hebbian (HBP) and heterosynaptic plasticity (HSP) may emerge from the same underlying dynamics, thus providing a unifying explanation. It also suggests an alternative perspective of neuroplasticity, where HSP is promoted to the primary learning and memory mechanism, and HBP is an emergent byproduct. We present simulations that show that (a) HSP can explain the metaplasticity of neurons, (b) HSP can explain the flexibility of the biology circuits, and (c) gradient learning can arise quickly from simple evolutionary dynamics that do not compute any explicit gradient. While our primary focus is on biology, the principle also implies a new approach to designing AI training algorithms and physically learnable AI hardware. Conceptually, our result demonstrates that contrary to the common belief, gradient computation may be extremely easy and common in nature.

q-bio.NC↗

arXiv2025

Formation of Representations in Neural Networks

Understanding neural representations will help open the black box of neural networks and advance our scientific understanding of modern AI systems. However, how complex, structured, and transferable representations emerge in modern neural networks has remained a mystery. Building on previous results, we propose the Canonical Representation Hypothesis (CRH), which posits a set of six alignment relations to universally govern the formation of representations in most hidden layers of a neural network. Under the CRH, the latent representations (R), weights (W), and neuron gradients (G) become mutually aligned during training. This alignment implies that neural networks naturally learn compact representations, where neurons and weights are invariant to task-irrelevant transformations. We then show that the breaking of CRH leads to the emergence of reciprocal power-law relations between R, W, and G, which we refer to as the Polynomial Alignment Hypothesis (PAH). We present a minimal-assumption theory proving that the balance between gradient noise and regularization is crucial for the emergence of the canonical representation. The CRH and PAH lead to an exciting possibility of unifying major key deep learning phenomena, including neural collapse and the neural feature ansatz, in a single framework.

cs.LG↗

arXiv2025

What if Eye...? Computationally Recreating Vision Evolution

Vision systems in nature show remarkable diversity, from simple light-sensitive patches to complex camera eyes with lenses. While natural selection has produced these eyes through countless mutations over millions of years, they represent just one set of realized evolutionary paths. Testing hypotheses about how environmental pressures shaped eye evolution remains challenging since we cannot experimentally isolate individual factors. Computational evolution offers a way to systematically explore alternative trajectories. Here we show how environmental demands drive three fundamental aspects of visual evolution through an artificial evolution framework that co-evolves both physical eye structure and neural processing in embodied agents. First, we demonstrate computational evidence that task specific selection drives bifurcation in eye evolution - orientation tasks like navigation in a maze leads to distributed compound-type eyes while an object discrimination task leads to the emergence of high-acuity camera-type eyes. Second, we reveal how optical innovations like lenses naturally emerge to resolve fundamental tradeoffs between light collection and spatial precision. Third, we uncover systematic scaling laws between visual acuity and neural processing, showing how task complexity drives coordinated evolution of sensory and computational capabilities. Our work introduces a novel paradigm that illuminates evolutionary principles shaping vision by creating targeted single-player games where embodied agents must simultaneously evolve visual systems and learn complex behaviors. Through our unified genetic encoding framework, these embodied agents serve as next-generation hypothesis testing machines while providing a foundation for designing manufacturable bio-inspired vision systems. Website: http://eyes.mit.edu/

cs.AI↗

arXiv2024

On Generalization Bounds for Neural Networks with Low Rank Layers

While previous optimization results have suggested that deep neural networks tend to favour low-rank weight matrices, the implications of this inductive bias on generalization bounds remain underexplored. In this paper, we apply Maurer's chain rule for Gaussian complexity to analyze how low-rank layers in deep networks can prevent the accumulation of rank and dimensionality factors that typically multiply across layers. This approach yields generalization bounds for rank and spectral norm constrained networks. We compare our results to prior generalization bounds for deep networks, highlighting how deep networks with low-rank layers can achieve better generalization than those with full-rank layers. Additionally, we discuss how this framework provides new perspectives on the generalization capabilities of deep networks exhibiting neural collapse.

cs.LG↗

arXiv2024

SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network

We investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate that training with mini-batch SGD and weight decay induces a bias toward rank minimization in the weight matrices. Specifically, we show both theoretically and empirically that this bias becomes more pronounced with smaller batch sizes, higher learning rates, or stronger weight decay. Additionally, we predict and empirically confirm that weight decay is essential for this bias to occur. Unlike previous literature, our analysis does not rely on assumptions about the data, convergence, or optimality of the weight matrices, making it applicable to a wide range of neural network architectures of any width or depth. Finally, we empirically explore the connection between this bias and generalization, finding that it has a marginal effect on the test performance.

cs.LG↗

arXiv2024

Iterative regularization in classification via hinge loss diagonal descent

Iterative regularization is a classic idea in regularization theory, that has recently become popular in machine learning. On the one hand, it allows to design efficient algorithms controlling at the same time numerical and statistical accuracy. On the other hand it allows to shed light on the learning curves observed while training neural networks. In this paper, we focus on iterative regularization in the context of classification. After contrasting this setting with that of linear inverse problems, we develop an iterative regularization approach based on the use of the hinge loss function. More precisely we consider a diagonal approach for a family of algorithms for which we prove convergence as well as rates of convergence and stability results for a suitable classification noise model. Our approach compares favorably with other alternatives, as confirmed by numerical simulations.

stat.ML↗

arXiv2024

On the Power of Decision Trees in Auto-Regressive Language Modeling

Originally proposed for handling time series data, Auto-regressive Decision Trees (ARDTs) have not yet been explored for language modeling. This paper delves into both the theoretical and practical applications of ARDTs in this new context. We theoretically demonstrate that ARDTs can compute complex functions, such as simulating automata, Turing machines, and sparse circuits, by leveraging "chain-of-thought" computations. Our analysis provides bounds on the size, depth, and computational efficiency of ARDTs, highlighting their surprising computational power. Empirically, we train ARDTs on simple language generation tasks, showing that they can learn to generate coherent and grammatically correct text on par with a smaller Transformer model. Additionally, we show that ARDTs can be used on top of transformer representations to solve complex reasoning tasks. This research reveals the unique computational abilities of ARDTs, aiming to broaden the architectural diversity in language model development.

cs.CL↗

arXiv2024

How Neural Networks Learn the Support is an Implicit Regularization Effect of SGD

We investigate the ability of deep neural networks to identify the support of the target function. Our findings reveal that mini-batch SGD effectively learns the support in the first layer of the network by shrinking to zero the weights associated with irrelevant components of input. In contrast, we demonstrate that while vanilla GD also approximates the target function, it requires an explicit regularization term to learn the support in the first layer. We prove that this property of mini-batch SGD is due to a second-order implicit regularization effect which is proportional to $η/ b$ (step size / batch size). Our results are not only another proof that implicit regularization has a significant impact on training optimization dynamics but they also shed light on the structure of the features that are learned by the network. Additionally, they suggest that smaller batches enhance feature interpretability and reduce dependency on initialization.

cs.LG↗

arXiv2023

System identification of neural systems: If we got it right, would we know?

Artificial neural networks are being proposed as models of parts of the brain. The networks are compared to recordings of biological neurons, and good performance in reproducing neural responses is considered to support the model's validity. A key question is how much this system identification approach tells us about brain computation. Does it validate one model architecture over another? We evaluate the most commonly used comparison techniques, such as a linear encoding model and centered kernel alignment, to correctly identify a model by replacing brain recordings with known ground truth models. System identification performance is quite variable; it also depends significantly on factors independent of the ground truth architecture, such as stimuli images. In addition, we show the limitations of using functional similarity scores in identifying higher-level architectural motifs.

q-bio.NC↗